[ { "step": 1, "loss": 2.3658299446105957, "lr": 1.99985736255971e-05, "bits": 32, "elapsed_s": 145.4 }, { "step": 2, "loss": 2.2756407260894775, "lr": 1.999429490929718e-05, "bits": 32, "elapsed_s": 206.4 }, { "step": 3, "loss": 2.417659282684326, "lr": 1.998716507171053e-05, "bits": 32, "elapsed_s": 210.0 }, { "step": 4, "loss": 2.3101353645324707, "lr": 1.997718614680071e-05, "bits": 32, "elapsed_s": 213.7 }, { "step": 5, "loss": 2.3069236278533936, "lr": 1.9964360981304334e-05, "bits": 32, "elapsed_s": 217.4 }, { "step": 6, "loss": 2.3993771076202393, "lr": 1.9948693233918955e-05, "bits": 32, "elapsed_s": 221.2 }, { "step": 7, "loss": 2.3634796142578125, "lr": 1.993018737425934e-05, "bits": 32, "elapsed_s": 224.9 }, { "step": 8, "loss": 2.296841621398926, "lr": 1.9908848681582398e-05, "bits": 32, "elapsed_s": 228.5 }, { "step": 9, "loss": 2.359053134918213, "lr": 1.9884683243281123e-05, "bits": 32, "elapsed_s": 232.2 }, { "step": 10, "loss": 2.3563246726989746, "lr": 1.9857697953148045e-05, "bits": 32, "elapsed_s": 235.9 }, { "step": 11, "loss": 2.2600417137145996, "lr": 1.982790050940859e-05, "bits": 32, "elapsed_s": 239.5 }, { "step": 12, "loss": 2.329841136932373, "lr": 1.9795299412524955e-05, "bits": 32, "elapsed_s": 243.1 }, { "step": 13, "loss": 2.2916908264160156, "lr": 1.9759903962771165e-05, "bits": 16, "elapsed_s": 403.0 }, { "step": 14, "loss": 2.2642662525177, "lr": 1.9721724257579918e-05, "bits": 16, "elapsed_s": 447.5 }, { "step": 15, "loss": 2.3322548866271973, "lr": 1.9680771188662054e-05, "bits": 16, "elapsed_s": 451.2 }, { "step": 16, "loss": 2.327916145324707, "lr": 1.963705643889942e-05, "bits": 16, "elapsed_s": 454.8 }, { "step": 17, "loss": 2.319948673248291, "lr": 1.9590592479012033e-05, "bits": 16, "elapsed_s": 458.6 }, { "step": 18, "loss": 2.3440849781036377, "lr": 1.95413925640005e-05, "bits": 16, "elapsed_s": 462.2 }, { "step": 19, "loss": 2.2415170669555664, "lr": 1.94894707293647e-05, "bits": 16, "elapsed_s": 466.0 }, { "step": 20, "loss": 2.2836086750030518, "lr": 1.9434841787099814e-05, "bits": 16, "elapsed_s": 469.7 }, { "step": 21, "loss": 2.241199254989624, "lr": 1.9377521321470816e-05, "bits": 16, "elapsed_s": 473.4 }, { "step": 22, "loss": 2.287238359451294, "lr": 1.9317525684566693e-05, "bits": 16, "elapsed_s": 477.1 }, { "step": 23, "loss": 2.249763011932373, "lr": 1.9254871991635605e-05, "bits": 16, "elapsed_s": 480.8 }, { "step": 24, "loss": 2.3067433834075928, "lr": 1.9189578116202315e-05, "bits": 16, "elapsed_s": 484.5 }, { "step": 25, "loss": 2.351858615875244, "lr": 1.9121662684969344e-05, "bits": 16, "elapsed_s": 488.3 }, { "step": 26, "loss": 2.2863049507141113, "lr": 1.905114507250322e-05, "bits": 16, "elapsed_s": 492.0 }, { "step": 27, "loss": 2.288116931915283, "lr": 1.8978045395707427e-05, "bits": 16, "elapsed_s": 495.7 }, { "step": 28, "loss": 2.3226139545440674, "lr": 1.8902384508083528e-05, "bits": 16, "elapsed_s": 499.3 }, { "step": 29, "loss": 2.3136937618255615, "lr": 1.8824183993782204e-05, "bits": 16, "elapsed_s": 503.0 }, { "step": 30, "loss": 2.2789459228515625, "lr": 1.8743466161445833e-05, "bits": 16, "elapsed_s": 506.7 }, { "step": 31, "loss": 2.2171008586883545, "lr": 1.86602540378444e-05, "bits": 16, "elapsed_s": 510.4 }, { "step": 32, "loss": 2.2828402519226074, "lr": 1.8574571361306522e-05, "bits": 16, "elapsed_s": 514.0 }, { "step": 33, "loss": 2.3170647621154785, "lr": 1.8486442574947524e-05, "bits": 16, "elapsed_s": 517.6 }, { "step": 34, "loss": 2.291591167449951, "lr": 1.83958928196964e-05, "bits": 16, "elapsed_s": 521.3 }, { "step": 35, "loss": 2.192140817642212, "lr": 1.8302947927123777e-05, "bits": 16, "elapsed_s": 525.0 }, { "step": 36, "loss": 2.225846529006958, "lr": 1.8207634412072775e-05, "bits": 16, "elapsed_s": 528.8 }, { "step": 37, "loss": 2.2373311519622803, "lr": 1.810997946509502e-05, "bits": 16, "elapsed_s": 532.5 }, { "step": 38, "loss": 2.257525682449341, "lr": 1.8010010944693853e-05, "bits": 16, "elapsed_s": 536.2 }, { "step": 39, "loss": 2.2118940353393555, "lr": 1.790775736937699e-05, "bits": 16, "elapsed_s": 539.8 }, { "step": 40, "loss": 2.290553092956543, "lr": 1.7803247909520927e-05, "bits": 16, "elapsed_s": 543.5 }, { "step": 41, "loss": 2.196901798248291, "lr": 1.7696512379049333e-05, "bits": 16, "elapsed_s": 547.1 }, { "step": 42, "loss": 2.273902416229248, "lr": 1.7587581226927918e-05, "bits": 16, "elapsed_s": 550.8 }, { "step": 43, "loss": 2.3220043182373047, "lr": 1.7476485528478103e-05, "bits": 16, "elapsed_s": 554.4 }, { "step": 44, "loss": 2.173083782196045, "lr": 1.7363256976511986e-05, "bits": 16, "elapsed_s": 558.1 }, { "step": 45, "loss": 2.2635390758514404, "lr": 1.724792787229121e-05, "bits": 16, "elapsed_s": 561.8 }, { "step": 46, "loss": 2.189042806625366, "lr": 1.7130531116312216e-05, "bits": 16, "elapsed_s": 565.5 }, { "step": 47, "loss": 2.284858226776123, "lr": 1.7011100198920538e-05, "bits": 16, "elapsed_s": 569.1 }, { "step": 48, "loss": 2.293029308319092, "lr": 1.688966919075688e-05, "bits": 16, "elapsed_s": 572.8 }, { "step": 49, "loss": 2.208221673965454, "lr": 1.676627273303759e-05, "bits": 16, "elapsed_s": 576.5 }, { "step": 50, "loss": 2.2609944343566895, "lr": 1.6640946027672405e-05, "bits": 16, "elapsed_s": 580.2 }, { "step": 51, "loss": 2.241244316101074, "lr": 1.651372482722224e-05, "bits": 16, "elapsed_s": 583.9 }, { "step": 52, "loss": 2.2430310249328613, "lr": 1.6384645424699852e-05, "bits": 16, "elapsed_s": 587.6 }, { "step": 53, "loss": 2.224806785583496, "lr": 1.6253744643216387e-05, "bits": 16, "elapsed_s": 591.2 }, { "step": 54, "loss": 2.254180431365967, "lr": 1.6121059825476648e-05, "bits": 16, "elapsed_s": 594.9 }, { "step": 55, "loss": 2.187408685684204, "lr": 1.5986628823126168e-05, "bits": 16, "elapsed_s": 598.6 }, { "step": 56, "loss": 2.242783784866333, "lr": 1.5850489985953093e-05, "bits": 16, "elapsed_s": 602.3 }, { "step": 57, "loss": 2.274005889892578, "lr": 1.571268215094794e-05, "bits": 16, "elapsed_s": 606.1 }, { "step": 58, "loss": 2.2266464233398438, "lr": 1.557324463122438e-05, "bits": 16, "elapsed_s": 609.8 }, { "step": 59, "loss": 2.244105339050293, "lr": 1.5432217204804206e-05, "bits": 16, "elapsed_s": 613.5 }, { "step": 60, "loss": 2.1662049293518066, "lr": 1.5289640103269643e-05, "bits": 16, "elapsed_s": 617.1 }, { "step": 61, "loss": 2.2268805503845215, "lr": 1.5145554000286308e-05, "bits": 16, "elapsed_s": 620.9 }, { "step": 62, "loss": 2.2255120277404785, "lr": 1.5000000000000017e-05, "bits": 16, "elapsed_s": 624.5 }, { "step": 63, "loss": 2.220292568206787, "lr": 1.4853019625310828e-05, "bits": 16, "elapsed_s": 628.5 }, { "step": 64, "loss": 2.188319444656372, "lr": 1.4704654806027575e-05, "bits": 16, "elapsed_s": 632.2 }, { "step": 65, "loss": 2.2121450901031494, "lr": 1.455494786690636e-05, "bits": 16, "elapsed_s": 635.8 }, { "step": 66, "loss": 2.2020201683044434, "lr": 1.4403941515576361e-05, "bits": 16, "elapsed_s": 639.6 }, { "step": 67, "loss": 2.1953623294830322, "lr": 1.4251678830356425e-05, "bits": 16, "elapsed_s": 643.3 }, { "step": 68, "loss": 2.197232484817505, "lr": 1.4098203247965892e-05, "bits": 16, "elapsed_s": 647.0 }, { "step": 69, "loss": 2.212214946746826, "lr": 1.3943558551133203e-05, "bits": 16, "elapsed_s": 650.7 }, { "step": 70, "loss": 2.2386984825134277, "lr": 1.3787788856105777e-05, "bits": 16, "elapsed_s": 654.3 }, { "step": 71, "loss": 2.1566648483276367, "lr": 1.3630938600064761e-05, "bits": 16, "elapsed_s": 658.1 }, { "step": 72, "loss": 2.175183057785034, "lr": 1.3473052528448216e-05, "bits": 16, "elapsed_s": 661.8 }, { "step": 73, "loss": 2.182250738143921, "lr": 1.3314175682186372e-05, "bits": 16, "elapsed_s": 665.5 }, { "step": 74, "loss": 2.229224681854248, "lr": 1.3154353384852566e-05, "bits": 16, "elapsed_s": 669.3 }, { "step": 75, "loss": 2.214982748031616, "lr": 1.2993631229733592e-05, "bits": 16, "elapsed_s": 673.1 }, { "step": 76, "loss": 2.2187764644622803, "lr": 1.2832055066823055e-05, "bits": 16, "elapsed_s": 676.8 }, { "step": 77, "loss": 2.258338689804077, "lr": 1.2669670989741529e-05, "bits": 16, "elapsed_s": 680.6 }, { "step": 78, "loss": 2.128751039505005, "lr": 1.2506525322587217e-05, "bits": 16, "elapsed_s": 684.3 }, { "step": 79, "loss": 2.18953800201416, "lr": 1.2342664606720833e-05, "bits": 16, "elapsed_s": 688.0 }, { "step": 80, "loss": 2.1987457275390625, "lr": 1.2178135587488525e-05, "bits": 16, "elapsed_s": 691.7 }, { "step": 81, "loss": 2.313851833343506, "lr": 1.2012985200886612e-05, "bits": 16, "elapsed_s": 695.4 }, { "step": 82, "loss": 2.251089096069336, "lr": 1.1847260560171905e-05, "bits": 16, "elapsed_s": 699.1 }, { "step": 83, "loss": 2.218010902404785, "lr": 1.1681008942421492e-05, "bits": 16, "elapsed_s": 702.8 }, { "step": 84, "loss": 2.1430342197418213, "lr": 1.1514277775045777e-05, "bits": 16, "elapsed_s": 706.5 }, { "step": 85, "loss": 2.1426374912261963, "lr": 1.1347114622258621e-05, "bits": 16, "elapsed_s": 710.2 }, { "step": 86, "loss": 2.2420055866241455, "lr": 1.1179567171508471e-05, "bits": 16, "elapsed_s": 714.0 }, { "step": 87, "loss": 2.211289882659912, "lr": 1.101168321987433e-05, "bits": 16, "elapsed_s": 717.8 }, { "step": 88, "loss": 2.247645139694214, "lr": 1.0843510660430458e-05, "bits": 16, "elapsed_s": 721.6 }, { "step": 89, "loss": 2.2245328426361084, "lr": 1.067509746858366e-05, "bits": 16, "elapsed_s": 725.4 }, { "step": 90, "loss": 2.1795501708984375, "lr": 1.0506491688387136e-05, "bits": 16, "elapsed_s": 729.2 }, { "step": 91, "loss": 2.296074628829956, "lr": 1.0337741418834692e-05, "bits": 16, "elapsed_s": 733.0 }, { "step": 92, "loss": 2.1927618980407715, "lr": 1.0168894800139322e-05, "bits": 16, "elapsed_s": 736.7 }, { "step": 93, "loss": 2.2684683799743652, "lr": 1.0000000000000013e-05, "bits": 16, "elapsed_s": 740.5 }, { "step": 94, "loss": 2.145488739013672, "lr": 9.831105199860699e-06, "bits": 16, "elapsed_s": 807.6 }, { "step": 95, "loss": 2.1651835441589355, "lr": 9.662258581165328e-06, "bits": 16, "elapsed_s": 811.3 }, { "step": 96, "loss": 2.219163179397583, "lr": 9.493508311612883e-06, "bits": 16, "elapsed_s": 815.1 }, { "step": 97, "loss": 2.156376361846924, "lr": 9.324902531416357e-06, "bits": 16, "elapsed_s": 818.8 }, { "step": 98, "loss": 2.214916229248047, "lr": 9.156489339569562e-06, "bits": 16, "elapsed_s": 822.6 }, { "step": 99, "loss": 2.1308915615081787, "lr": 8.988316780125685e-06, "bits": 16, "elapsed_s": 826.3 }, { "step": 100, "loss": 2.1864893436431885, "lr": 8.820432828491547e-06, "bits": 16, "elapsed_s": 830.1 }, { "step": 101, "loss": 2.1464409828186035, "lr": 8.652885377741399e-06, "bits": 16, "elapsed_s": 833.8 }, { "step": 102, "loss": 2.193824052810669, "lr": 8.485722224954242e-06, "bits": 16, "elapsed_s": 837.5 }, { "step": 103, "loss": 2.1621243953704834, "lr": 8.318991057578528e-06, "bits": 16, "elapsed_s": 841.1 }, { "step": 104, "loss": 2.18757700920105, "lr": 8.152739439828115e-06, "bits": 16, "elapsed_s": 844.7 }, { "step": 105, "loss": 2.212999105453491, "lr": 7.987014799113405e-06, "bits": 16, "elapsed_s": 848.4 }, { "step": 106, "loss": 2.151425838470459, "lr": 7.821864412511492e-06, "bits": 16, "elapsed_s": 852.0 }, { "step": 107, "loss": 2.092022180557251, "lr": 7.657335393279186e-06, "bits": 16, "elapsed_s": 855.7 }, { "step": 108, "loss": 2.1615066528320312, "lr": 7.493474677412802e-06, "bits": 16, "elapsed_s": 859.3 }, { "step": 109, "loss": 2.160372257232666, "lr": 7.330329010258491e-06, "bits": 16, "elapsed_s": 862.9 }, { "step": 110, "loss": 2.1761460304260254, "lr": 7.167944933176965e-06, "bits": 16, "elapsed_s": 866.5 }, { "step": 111, "loss": 2.1427860260009766, "lr": 7.006368770266428e-06, "bits": 16, "elapsed_s": 870.3 }, { "step": 112, "loss": 2.1860930919647217, "lr": 6.84564661514745e-06, "bits": 16, "elapsed_s": 874.0 }, { "step": 113, "loss": 2.2383837699890137, "lr": 6.685824317813648e-06, "bits": 16, "elapsed_s": 877.7 }, { "step": 114, "loss": 2.223217248916626, "lr": 6.526947471551804e-06, "bits": 16, "elapsed_s": 881.5 }, { "step": 115, "loss": 2.2082157135009766, "lr": 6.369061399935259e-06, "bits": 16, "elapsed_s": 885.2 }, { "step": 116, "loss": 2.1652727127075195, "lr": 6.212211143894244e-06, "bits": 16, "elapsed_s": 889.0 }, { "step": 117, "loss": 2.200998067855835, "lr": 6.05644144886682e-06, "bits": 16, "elapsed_s": 892.6 }, { "step": 118, "loss": 2.2166528701782227, "lr": 5.901796752034131e-06, "bits": 16, "elapsed_s": 896.4 }, { "step": 119, "loss": 2.1170847415924072, "lr": 5.748321169643599e-06, "bits": 16, "elapsed_s": 900.0 }, { "step": 120, "loss": 2.2742390632629395, "lr": 5.596058484423664e-06, "bits": 16, "elapsed_s": 903.7 }, { "step": 121, "loss": 2.185448169708252, "lr": 5.445052133093663e-06, "bits": 16, "elapsed_s": 907.4 }, { "step": 122, "loss": 2.1917667388916016, "lr": 5.295345193972448e-06, "bits": 16, "elapsed_s": 911.1 }, { "step": 123, "loss": 2.185103416442871, "lr": 5.1469803746891945e-06, "bits": 8, "elapsed_s": 915.2 }, { "step": 124, "loss": 2.21760892868042, "lr": 5.000000000000005e-06, "bits": 8, "elapsed_s": 918.9 }, { "step": 125, "loss": 2.2185637950897217, "lr": 4.854445999713717e-06, "bits": 8, "elapsed_s": 922.6 }, { "step": 126, "loss": 2.2761147022247314, "lr": 4.710359896730377e-06, "bits": 8, "elapsed_s": 926.6 }, { "step": 127, "loss": 2.222972869873047, "lr": 4.567782795195815e-06, "bits": 8, "elapsed_s": 930.3 }, { "step": 128, "loss": 2.2304177284240723, "lr": 4.426755368775639e-06, "bits": 8, "elapsed_s": 934.0 }, { "step": 129, "loss": 2.2026565074920654, "lr": 4.287317849052081e-06, "bits": 8, "elapsed_s": 937.8 }, { "step": 130, "loss": 2.164916515350342, "lr": 4.149510014046927e-06, "bits": 8, "elapsed_s": 941.4 }, { "step": 131, "loss": 2.1385650634765625, "lr": 4.013371176873851e-06, "bits": 8, "elapsed_s": 945.1 }, { "step": 132, "loss": 2.180548667907715, "lr": 3.878940174523373e-06, "bits": 8, "elapsed_s": 948.8 }, { "step": 133, "loss": 2.1922061443328857, "lr": 3.746255356783634e-06, "bits": 8, "elapsed_s": 952.5 }, { "step": 134, "loss": 2.2024588584899902, "lr": 3.6153545753001675e-06, "bits": 8, "elapsed_s": 956.2 }, { "step": 135, "loss": 2.174429178237915, "lr": 3.486275172777781e-06, "bits": 8, "elapsed_s": 959.8 }, { "step": 136, "loss": 2.1747477054595947, "lr": 3.3590539723276095e-06, "bits": 8, "elapsed_s": 963.5 }, { "step": 137, "loss": 2.141603469848633, "lr": 3.233727266962427e-06, "bits": 8, "elapsed_s": 967.2 }, { "step": 138, "loss": 2.22629451751709, "lr": 3.1103308092431357e-06, "bits": 8, "elapsed_s": 970.8 }, { "step": 139, "loss": 2.1893129348754883, "lr": 2.988899801079476e-06, "bits": 8, "elapsed_s": 974.5 }, { "step": 140, "loss": 2.283906936645508, "lr": 2.8694688836877998e-06, "bits": 8, "elapsed_s": 978.1 }, { "step": 141, "loss": 2.2004716396331787, "lr": 2.752072127708804e-06, "bits": 8, "elapsed_s": 981.8 }, { "step": 142, "loss": 2.084562063217163, "lr": 2.6367430234880278e-06, "bits": 8, "elapsed_s": 985.4 }, { "step": 143, "loss": 2.0774576663970947, "lr": 2.523514471521911e-06, "bits": 8, "elapsed_s": 989.2 }, { "step": 144, "loss": 2.22298264503479, "lr": 2.412418773072093e-06, "bits": 8, "elapsed_s": 992.9 }, { "step": 145, "loss": 2.2004783153533936, "lr": 2.3034876209506785e-06, "bits": 8, "elapsed_s": 996.5 }, { "step": 146, "loss": 2.1475512981414795, "lr": 2.196752090479084e-06, "bits": 8, "elapsed_s": 1000.2 }, { "step": 147, "loss": 2.153198719024658, "lr": 2.0922426306230134e-06, "bits": 8, "elapsed_s": 1003.9 }, { "step": 148, "loss": 2.15569806098938, "lr": 1.989989055306154e-06, "bits": 8, "elapsed_s": 1007.6 }, { "step": 149, "loss": 2.235653877258301, "lr": 1.8900205349049891e-06, "bits": 8, "elapsed_s": 1011.3 }, { "step": 150, "loss": 2.156966209411621, "lr": 1.792365587927238e-06, "bits": 8, "elapsed_s": 1015.0 }, { "step": 151, "loss": 2.1192023754119873, "lr": 1.697052072876238e-06, "bits": 8, "elapsed_s": 1018.7 }, { "step": 152, "loss": 2.1768195629119873, "lr": 1.6041071803036128e-06, "bits": 8, "elapsed_s": 1022.4 }, { "step": 153, "loss": 2.2243118286132812, "lr": 1.5135574250524902e-06, "bits": 8, "elapsed_s": 1026.0 }, { "step": 154, "loss": 2.1157987117767334, "lr": 1.4254286386934894e-06, "bits": 8, "elapsed_s": 1029.8 }, { "step": 155, "loss": 2.178826332092285, "lr": 1.3397459621556134e-06, "bits": 8, "elapsed_s": 1033.5 }, { "step": 156, "loss": 2.223170280456543, "lr": 1.2565338385541797e-06, "bits": 8, "elapsed_s": 1037.1 }, { "step": 157, "loss": 2.2212882041931152, "lr": 1.1758160062178097e-06, "bits": 8, "elapsed_s": 1040.8 }, { "step": 158, "loss": 2.7814295291900635, "lr": 1.0976154919164855e-06, "bits": 4, "elapsed_s": 1044.9 }, { "step": 159, "loss": 3.052875518798828, "lr": 1.0219546042925849e-06, "bits": 4, "elapsed_s": 1048.8 }, { "step": 160, "loss": 3.07733154296875, "lr": 9.488549274967878e-07, "bits": 4, "elapsed_s": 1052.5 }, { "step": 161, "loss": 2.9882161617279053, "lr": 8.783373150306667e-07, "bits": 4, "elapsed_s": 1056.3 }, { "step": 162, "loss": 3.018219470977783, "lr": 8.104218837976945e-07, "bits": 4, "elapsed_s": 1060.0 }, { "step": 163, "loss": 3.0597972869873047, "lr": 7.451280083644057e-07, "bits": 4, "elapsed_s": 1063.7 }, { "step": 164, "loss": 3.0820038318634033, "lr": 6.824743154333161e-07, "bits": 4, "elapsed_s": 1067.5 }, { "step": 165, "loss": 2.9962010383605957, "lr": 6.224786785291973e-07, "bits": 4, "elapsed_s": 1071.1 }, { "step": 166, "loss": 3.0425121784210205, "lr": 5.651582129001979e-07, "bits": 4, "elapsed_s": 1074.8 }, { "step": 167, "loss": 3.118518114089966, "lr": 5.105292706353095e-07, "bits": 4, "elapsed_s": 1078.5 }, { "step": 168, "loss": 3.0715575218200684, "lr": 4.586074359995121e-07, "bits": 4, "elapsed_s": 1082.2 }, { "step": 169, "loss": 3.0787503719329834, "lr": 4.094075209879791e-07, "bits": 4, "elapsed_s": 1085.8 }, { "step": 170, "loss": 3.1245131492614746, "lr": 3.6294356110059177e-07, "bits": 4, "elapsed_s": 1089.5 }, { "step": 171, "loss": 3.1227684020996094, "lr": 3.1922881133795837e-07, "bits": 4, "elapsed_s": 1093.2 }, { "step": 172, "loss": 3.0993998050689697, "lr": 2.7827574242009445e-07, "bits": 4, "elapsed_s": 1096.9 }, { "step": 173, "loss": 3.082979917526245, "lr": 2.400960372288475e-07, "bits": 4, "elapsed_s": 1100.5 }, { "step": 174, "loss": 3.078078031539917, "lr": 2.0470058747505524e-07, "bits": 4, "elapsed_s": 1104.2 }, { "step": 175, "loss": 3.085704803466797, "lr": 1.720994905914209e-07, "bits": 4, "elapsed_s": 1108.0 }, { "step": 176, "loss": 3.043865203857422, "lr": 1.423020468519632e-07, "bits": 4, "elapsed_s": 1111.7 }, { "step": 177, "loss": 3.049015522003174, "lr": 1.1531675671888625e-07, "bits": 4, "elapsed_s": 1115.5 }, { "step": 178, "loss": 3.1806159019470215, "lr": 9.115131841761164e-08, "bits": 4, "elapsed_s": 1119.3 }, { "step": 179, "loss": 3.1234114170074463, "lr": 6.981262574066397e-08, "bits": 4, "elapsed_s": 1123.0 }, { "step": 180, "loss": 3.0956645011901855, "lr": 5.1306766081048476e-08, "bits": 4, "elapsed_s": 1126.8 }, { "step": 181, "loss": 3.007459878921509, "lr": 3.5639018695670117e-08, "bits": 4, "elapsed_s": 1130.5 }, { "step": 182, "loss": 3.145798921585083, "lr": 2.2813853199292755e-08, "bits": 4, "elapsed_s": 1134.3 }, { "step": 183, "loss": 3.076660394668579, "lr": 1.2834928289472419e-08, "bits": 4, "elapsed_s": 1138.0 }, { "step": 184, "loss": 3.0217347145080566, "lr": 5.705090702819995e-09, "bits": 4, "elapsed_s": 1141.8 }, { "step": 185, "loss": 3.11957049369812, "lr": 1.4263744029019428e-09, "bits": 4, "elapsed_s": 1145.5 }, { "step": 186, "loss": 3.1024274826049805, "lr": 0.0, "bits": 4, "elapsed_s": 1149.3 } ]